© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 259755
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    扆
    0.59
    ovjek
    0.56
    zoeken
    0.53
    рье
    0.53
    utscher
    0.51
    )';
    0.48
    ӡ
    0.48
     ভাষণ
    0.48
     Fee
    0.48
    чих
    0.46
    POSITIVE LOGITS
     as
    0.54
     depths
    0.54
    ل
    0.54
     questions
    0.53
    depth
    0.53
    ان
    0.52
     layers
    0.51
    ب
    0.51
     wavelengths
    0.50
     deno
    0.49
    Activations Density 0.000%

    No Known Activations